dopt.nnet.layers

Modules

batchnorm

module dopt.nnet.layers.batchnorm

Contains an implementation of batch normalisation.

conv

module dopt.nnet.layers.conv

Contains an implementation of convolutional layers.

datasource

module dopt.nnet.layers.datasource

Allows one to provide input to a network via a dopt variable.

dense

module dopt.nnet.layers.dense

Contains an implementation of dense (i.e., fully connected) layers.

dropout

module dopt.nnet.layers.dropout

Contains an implementation of dropout.

maxpool

module dopt.nnet.layers.maxpool

Contains an implementation of max pooling.

relu

module dopt.nnet.layers.relu

Contains an implementation of the ReLU activation function.

softmax

module dopt.nnet.layers.softmax

Contains an implementation of the softmat activation function.

Public Imports

dopt.nnet.layers.batchnorm

public import dopt.nnet.layers.batchnorm;

dopt.nnet.layers.conv

public import dopt.nnet.layers.conv;

dopt.nnet.layers.datasource

public import dopt.nnet.layers.datasource;

dopt.nnet.layers.dense

public import dopt.nnet.layers.dense;

dopt.nnet.layers.dropout

public import dopt.nnet.layers.dropout;

dopt.nnet.layers.maxpool

public import dopt.nnet.layers.maxpool;

dopt.nnet.layers.relu

public import dopt.nnet.layers.relu;

dopt.nnet.layers.softmax

public import dopt.nnet.layers.softmax;

Members

Classes

Layer

class Layer

Encapsulates the expressions and parameter information that defines a network layer.

Functions

topologicalSort

Layer[] topologicalSort(Layer[] ops)

Undocumented in source. Be warned that the author may not have intended to support it.

• data
• layers
• lipschitz
• losses
• models
• networks
• parameters
• util